CN116403234A - Automatic prediction method for building engineering structure calculation based on CAD drawing - Google Patents
Automatic prediction method for building engineering structure calculation based on CAD drawing Download PDFInfo
- Publication number
- CN116403234A CN116403234A CN202211485132.9A CN202211485132A CN116403234A CN 116403234 A CN116403234 A CN 116403234A CN 202211485132 A CN202211485132 A CN 202211485132A CN 116403234 A CN116403234 A CN 116403234A
- Authority
- CN
- China
- Prior art keywords
- calculation
- engineering structure
- building
- building engineering
- cad
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000005516 engineering process Methods 0.000 claims abstract description 32
- 238000010276 construction Methods 0.000 claims abstract description 22
- 230000002787 reinforcement Effects 0.000 claims abstract description 17
- 238000003058 natural language processing Methods 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 3
- 238000001514 detection method Methods 0.000 claims description 12
- 229910001294 Reinforcing steel Inorganic materials 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000009877 rendering Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000003014 reinforcing effect Effects 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 3
- 239000002689 soil Substances 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims 1
- 230000010365 information processing Effects 0.000 abstract description 3
- 238000009434 installation Methods 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 210000002435 tendon Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/19007—Matching; Proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An automatic prediction method for the calculation amount of a building engineering structure based on CAD drawings belongs to the field of engineering drawing image recognition. Aiming at the problem of long time consumption of manual calculation of engineering quantity, the invention automatically picks up component information and drawing content in the drawing by constructing a method based on image recognition; the natural language processing technology is utilized to realize the extraction of the table and the text content in the drawing, and the information processing efficiency is improved; matching between reinforcement information and components is achieved through a machine learning technology, automation of structural calculation is achieved through a pre-built calculation formula library, an engineering quantity and a valuation list are automatically generated through cooperation of a unit price database, and prediction efficiency of the engineering calculation is improved. The method is suitable for the fields of civil construction, engineering installation and the like, and the engineering quantity is automatically predicted by the image recognition and machine learning technology, so that the engineering quantity prediction efficiency is improved.
Description
Technical Field
The invention relates to a CAD drawing-based automatic prediction method for the calculated amount of a building engineering structure, and belongs to the field of engineering drawing image recognition.
Technical Field
Along with the rapid development of economy, the construction industry has also been greatly developed. In the engineering construction process, in order to ensure the economic benefit of engineering construction, it is often necessary to control the cost of the project. The determination of the construction cost is based on the number of the construction entities to be completed by the construction, the number of the construction entities is calculated correctly and expressed in a certain measurement unit, and the construction measurement, namely the calculation of the construction quantity is needed to be used as the basis for determining the construction cost.
The engineering quantity is the number of individual sub-engineering and structural members expressed in physical or natural units of measurement. Physical measurement units generally refer to length, area, volume, weight, etc. expressed in metric measurements. For example, the stair railing takes 'rice' as a measuring unit; wall plastering takes square meters as a measuring unit; concrete takes cubic meters as a measuring unit; and the processing, binding and installing of the steel bars take ton as a measuring unit. The natural measurement unit mainly refers to the engineering quantity expressed by taking the object itself as a measurement unit. For example, the brick sewage bucket takes 'one' as a measuring unit; the equipment installation engineering takes a table, a sleeve, a group, a piece and the like as measurement units.
The engineering measurement is used as a core basic link of engineering cost, at present, manual calculation or software flow modeling operation is relied on, and the time for manually calculating a building to build a residential building is generally about one week. The calculation efficiency is low, and the engineering propulsion is affected to a certain extent.
Disclosure of Invention
Aiming at the problem of long time consumption for manually calculating the engineering quantity, the invention mainly aims to provide an automatic prediction method for the construction engineering structure calculated quantity based on CAD drawings, which automatically calculates the engineering quantity through image recognition and machine learning technology and improves the prediction efficiency of the engineering quantity.
The invention aims at realizing the following technical scheme:
the invention discloses a CAD drawing-based automatic prediction method for the calculation amount of a building engineering structure, which is used for automatically picking up component information and drawing content in a drawing by constructing a method based on image recognition; the natural language processing technology is utilized to realize the extraction of the table and the text content in the drawing, and the information processing efficiency is improved; matching between reinforcement information and components is achieved through a machine learning technology, automation of structural calculation is achieved through a pre-built calculation formula library, an engineering quantity and a valuation list are automatically generated through cooperation of a unit price database, and prediction efficiency of the engineering calculation is improved.
The invention discloses a CAD drawing-based automatic prediction method for the calculated amount of a building engineering structure, which comprises the following steps:
step 1: and constructing a calculation formula library of the building engineering structure calculation.
In the structural calculation, three types of engineering calculation of concrete, reinforcing steel bars and templates are mainly performed.
1.1, constructing a volume calculation formula of a mixed soil wall, a beam, a plate, a column and a stair;
1.2, constructing a calculation formula of horizontal distribution ribs, vertical distribution ribs and lacing wires of the wall; stirrups of the beam, longitudinal ribs and structural rib calculation formulas; calculating formulas of the distribution ribs and the additional ribs of the plate; calculating formulas of longitudinal bars and stirrups of the column; the calculation formulas of the platform plate distribution bars of the stairs, the longitudinal bars of the stairs post, the stirrups of the stairs beam and the longitudinal bars are shown in the specification;
and 1.3, constructing a calculation formula of the template area.
Step 2: converting the engineering drawing into the type data to be identified.
2.1, rendering the vectorized drawing into an RGB image of a pixel level;
2.2, converting the vectorized drawing into tree data based on the layers, wherein the data of each layer is a geometric line segment of the corresponding layer.
Step 3: based on natural language processing technology and image processing technology, the drawing is divided and the category judgment is carried out.
Step 3.1: in the house construction drawing, one drawing contains all component contents of all floors, different contents are separated by boxes, and different contents in the drawing are segmented by using an image segmentation technology;
step 3.2: and 3.1, on the basis of the CAD drawing segmented in the step 3.1, recognizing the text of the drawing description by using a natural language processing technology, obtaining the types of the drawing, and respectively outputting the drawings of walls, beams, plates, columns and stairs of different floors.
Step 4: and identifying and extracting the components of the drawing by using an image identification technology.
Step 4.1: collecting a plurality of building CAD drawings, marking the component contents of walls, beams, plates, columns and stairs, and simultaneously constructing a geometric library of different components in the building CAD;
step 4.2: training the data marked in the step 4.1 by using a target detection algorithm, and storing model parameters after model convergence;
step 4.3: and detecting the components by using the trained target detection model, comparing the components with a geometric library, and comprehensively outputting the final geometric dimension of the components and the position information of the relative shaft network.
Step 5: and identifying the form of the drawing by utilizing image identification and natural language technology.
Step 5.1: collecting a plurality of building CAD drawings and marking the positions of the tables;
step 5.2: training the data marked in the step 5.1 by using a target detection algorithm, and storing model parameters after model convergence;
step 5.3: positioning the drawing form by using a target detection algorithm;
step 5.4: the contents of the table are identified using natural language processing techniques, and the floor height and the dimensions of the partial components are output. The table contents include a building height table and a size table.
Step 6: and extracting the reinforcement information by using a text processing technology.
Step 6.1: and (5) extracting the reinforcing bars according to the rule of labeling by a flat method based on the table extracted in the step (5).
Step 6.2: and converting the extracted rebar text into a dictionary defined in advance, and matching with a calculation formula.
Step 7: and outputting the constructed reinforcement information by using a machine learning technology.
And (3) matching the reinforcing steel bar dictionary obtained in the step (4) and the constructed positions, and outputting each constructed accurate matching dictionary.
Step 8: and (3) calculating the amount by using a calculation formula library and automatically outputting a calculation report, namely realizing automatic prediction of the calculation amount of the building engineering structure based on the CAD drawing.
And 2, obtaining construction geometric information and reinforcement information of each building, each layer of wall, beam, plate, column and stair in project engineering through steps 2 to 7, outputting concrete, reinforcement and template quantities of the final wall, beam, plate, column and stair by using a calculation formula, and generating engineering quantity and valuation list by combining local engineering quota data, namely realizing automatic prediction of building engineering structure calculation quantity based on CAD drawing.
The beneficial effects are that:
1. the invention discloses a CAD drawing-based automatic prediction method for the calculated amount of a building engineering structure, which is used for realizing automatic pickup of component information in a drawing and drawing content thereof by constructing an image recognition-based method and utilizing a natural language processing technology, so that the information processing efficiency is improved.
2. According to the automatic prediction method for the construction engineering structure calculation amount based on the CAD drawing, matching between construction reinforcement information and construction is achieved through a machine learning technology, finally automatic calculation of the construction calculation amount is achieved through a pre-built calculation formula library, an engineering amount and a valuation list are automatically generated by matching with a unit price database, and efficiency of the engineering calculation amount is improved.
Drawings
FIG. 1 is a flow chart of an automatic prediction method for building engineering structure calculation based on CAD drawing;
FIG. 2 is a plan view of a shear wall in this embodiment;
fig. 3 is a view of Liang Peijin in the present embodiment;
fig. 4 is a plate reinforcement diagram in the present embodiment;
FIG. 5 is a graph of the recognition result of the wall stud in the present embodiment;
fig. 6 is a diagram of beam recognition results in the present embodiment;
fig. 7 is a board recognition result chart in the present embodiment;
FIG. 8 is a three-dimensional model rendering result diagram of the recognition result in the present embodiment;
fig. 9 is a three-dimensional model rendering result diagram of the recognition result in the present embodiment.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings and examples. The technical problems and the beneficial effects solved by the technical proposal of the invention are also described, and the described embodiment is only used for facilitating the understanding of the invention and does not have any limiting effect.
As shown in fig. 1, the embodiment adopts the automatic calculation prediction method of the building engineering structure based on the CAD drawing disclosed by the invention to automatically calculate and predict concrete and reinforcing steel bars of a standard layer of one of the houses.
Step 1: and constructing a calculation formula library of the building engineering structure calculation.
In the structural calculation, the concrete and the steel bar are mainly calculated.
1.1, constructing a volume calculation formula of a wall, a beam, a plate, a column and a stair of the mixed soil
The specific formula volume V is as follows:
V＝S*H
s represents the bottom area and H represents the height
The bottom area calculating method comprises the following steps:
A. standard shape: the wall beam plate column stair is generally rectangular, and S=w (width) and l (length) of the regular rectangle are equal to each other
w represents the width of the rectangle, l represents the length of the rectangle
B. Profile: in the case of irregular polygonal area, a pattern rasterization area solving mode is used, the polygonal is marked as continuous points p1 and p2 … pn., the largest circumscribed rectangle is taken, then the rectangle is rasterized, whether the points are inside or outside the polygonal is judged, and finally the total number n of the inside points is calculated to be the total area of the unit point number area p_s.
1.2, constructing a calculation formula of horizontal distribution ribs, vertical distribution ribs and lacing wires of the wall;
stirrups, longitudinal bars, structural bars or torsion calculation formulas of the beams; calculating formulas of the distribution ribs and the additional ribs of the plate; calculating formulas of longitudinal bars and stirrups of the column; the platform plate distribution bars of the stair, the longitudinal bars of the stair columns, the stirrups of the stair beams and the calculation formulas of the longitudinal bars can be summarized into three types of stirrups, longitudinal bars and constructional bars (the distribution bars and the additional bars of the plates can be divided into longitudinal bars in the X direction and the Y direction):
stirrup weight w=cdr r p pi
Wherein C is the circumference of the stirrup, d is the number of stirrups (the arrangement length/the arrangement interval of the stirrups), r is the radius of the distributed stirrups, and p is the density of the reinforcing steel bars
The weight of the distribution bar w=l×d×r×r×p×pi
Wherein, L is the length of the distributed bars, d is the number of the distributed bars (the distance between the distributed length and the distributed direction), r is the radius of the distributed bars, and p is the density of the reinforced bars
Tendon weight w=ld r p pi
Wherein, the length of the L structural ribs, d is the number of the structural ribs (the arrangement length of the structural ribs/the interval in the arrangement direction), r is the radius of the distributed ribs, and p is the density of the reinforcing steel bars
Step 2: converting the engineering drawing into the type data to be identified.
2.1, rendering the CAD file into an RGB image at a pixel level through a graphic engine;
2.2, converting the vectorized drawing into tree data based on the layers, wherein the data of each layer is a geometric line segment of the corresponding layer.
3: based on natural language processing technology and image processing technology, the drawing is divided and the category judgment is carried out.
3.1: in the house building drawing, one drawing contains all component contents of all floors, different contents are separated by boxes, and different contents in the drawing are segmented by using an image segmentation technology.
3.2: and (3) identifying the text of the drawing description on the basis of the CAD drawing segmented in the step (3.1), obtaining the types of the drawing, and respectively outputting the drawings of walls, beams, plates, columns and stairs of different floors, wherein the original standard deviation wall column plate column drawing is shown in figures 2, 3 and 4.
4: and identifying and extracting the components of the drawing by using an image identification technology.
4.1: collecting one thousand or more building CAD drawings, manually marking the contents of the components of the wall, the beam, the plate, the column and the stairs, and simultaneously constructing a geometric library of different components in the building CAD;
4.2: training the data marked in the step 4.1 by using a target detection Faster-RCNN algorithm, and storing model parameters after model convergence;
4.3: and detecting the components by using the trained target detection model, comparing the components with a geometric library, and comprehensively outputting the final geometric dimension of the components and the position information of the relative shaft network, wherein the two-dimensional identification content is shown in fig. 5, 6 and 7.
5: and identifying the form of the drawing by utilizing image identification and natural language technology.
5.1: collecting a plurality of building CAD drawings and marking the positions of the tables;
5.2: training the data marked in the step 5.1 by using a target detection Faster-RCNN algorithm, and storing model parameters after model convergence;
5.3: positioning the drawing form by using a target detection Faster-RCNN algorithm;
5.4: the text classification technology and the regular expression are utilized to identify the content (building height table, size table) of the table, the floor height and the size of part of the components are output, and the 3D rendering of the identified result is shown in fig. 8 and 9 according to the floor height and the geometric information.
6: and extracting the reinforcement information by using a text processing technology.
6.1: and 5, extracting the reinforcing bars according to the table extracted in the step, and extracting the reinforcing bars according to the rule of labeling by a plain method.
6.2: and converting the extracted rebar text into a dictionary defined in advance, and matching with a calculation formula.
7: and finally outputting the constructed reinforcement information.
And (3) matching the reinforcing steel bar dictionary obtained in the step (4) and the constructed positions, and outputting each constructed accurate matching dictionary. And according to the text reinforcement information on the drawing, the stirrups, the tie bars and the distribution bars of the wall beam slab column are matched and identified.
8: and calculating the amount by using a calculation formula library and automatically outputting an amount calculation report.
And 2, obtaining construction geometric information and reinforcement information of each building, each layer of wall, beam, plate, column and stair in project engineering through steps 2 to 7, outputting concrete, reinforcement and template quantities of the final wall, beam, plate, column and stair by using a calculation formula, and generating an engineering quantity and a valuation list by combining local engineering quota data.
The 3F standard layer calculation result can be obtained according to the identification result and the calculation formula
The results were compared with the manual method as follows:
the error between the calculated result and the manual calculated result in the embodiment is within 2 percent, which meets the engineering cost requirement.
According to the automatic prediction method for the construction engineering structure calculation amount based on the CAD drawing, disclosed by the embodiment of the invention, the calculation of the engineering amount is completed in 5 minutes on a computer with a CPU being an I7 processor, and the time consumption is greatly reduced by about 5 hours for manually calculating a standard layer, so that the prediction efficiency of the engineering amount is improved.
The foregoing detailed description has set forth the objects, aspects and advantages of the invention in further detail, it should be understood that the foregoing description is only illustrative of the invention and is not intended to limit the scope of the invention, but is to be accorded the full scope of the invention as defined by the appended claims.
Claims (9)
1. A CAD drawing-based automatic prediction method for the calculation amount of a building engineering structure is characterized in that: comprises the following steps of the method,
step 1: constructing a calculation formula library of the building engineering structure calculation;
step 2: converting engineering drawings into type data to be identified;
step 3: based on natural language processing technology and image processing technology, carrying out segmentation and category judgment on the drawing;
step 4: carrying out recognition extraction on components of the drawing by utilizing an image recognition technology;
step 5: identifying the form of the drawing by utilizing image identification and natural language technology;
step 6: extracting reinforcement information by using a text processing technology;
step 7: outputting the constructed reinforcement information by utilizing a machine learning technology;
step 8: and (3) calculating the amount by using a calculation formula library and automatically outputting a calculation report, namely realizing automatic prediction of the calculation amount of the building engineering structure based on the CAD drawing.
2. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 1 is that,
1.1, constructing a volume calculation formula of a mixed soil wall, a beam, a plate, a column and a stair;
1.2, constructing a calculation formula of horizontal distribution ribs, vertical distribution ribs and lacing wires of the wall; stirrups of the beam, longitudinal ribs and structural rib calculation formulas; calculating formulas of the distribution ribs and the additional ribs of the plate; calculating formulas of longitudinal bars and stirrups of the column; the calculation formulas of the platform plate distribution bars of the stairs, the longitudinal bars of the stairs post, the stirrups of the stairs beam and the longitudinal bars are shown in the specification;
and 1.3, constructing a calculation formula of the template area.
3. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 2 is that,
2.1, rendering the vectorized drawing into an RGB image of a pixel level;
2.2, converting the vectorized drawing into tree data based on the layers, wherein the data of each layer is a geometric line segment of the corresponding layer.
4. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 3 is that,
step 3.1: in the house construction drawing, one drawing contains all component contents of all floors, different contents are separated by boxes, and different contents in the drawing are segmented by using an image segmentation technology;
step 3.2: and 3.1, on the basis of the CAD drawing segmented in the step 3.1, recognizing the text of the drawing description by using a natural language processing technology, obtaining the types of the drawing, and respectively outputting the drawings of walls, beams, plates, columns and stairs of different floors.
5. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 4 is that,
step 4.1: collecting a plurality of building CAD drawings, marking the component contents of walls, beams, plates, columns and stairs, and simultaneously constructing a geometric library of different components in the building CAD;
step 4.2: training the data marked in the step 4.1 by using a target detection algorithm, and storing model parameters after model convergence;
step 4.3: and detecting the components by using the trained target detection model, comparing the components with a geometric library, and comprehensively outputting the final geometric dimension of the components and the position information of the relative shaft network.
6. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 5 is that,
step 5.1: collecting a plurality of building CAD drawings and marking the positions of the tables;
step 5.2: training the data marked in the step 5.1 by using a target detection algorithm, and storing model parameters after model convergence;
step 5.3: positioning the drawing form by using a target detection algorithm;
step 5.4: identifying the contents of the table by using a natural language processing technology, and outputting the floor height and the size of a part of the components; the table contents include a building height table and a size table.
7. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 6 is that,
step 6.1: extracting reinforcing bars according to a plain method marking principle based on the table extracted in the step 5;
step 6.2: and converting the extracted rebar text into a dictionary defined in advance, and matching with a calculation formula.
8. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 7 is that,
and (3) matching the reinforcing steel bar dictionary obtained in the step (4) and the constructed positions, and outputting each constructed accurate matching dictionary.
9. The automatic prediction method for the calculation amount of the building engineering structure based on the CAD drawing as claimed in claim 1, wherein the method comprises the following steps of: the implementation method of the step 8 is that,
and 2, obtaining construction geometric information and reinforcement information of each building, each layer of wall, beam, plate, column and stair in project engineering through steps 2 to 7, outputting concrete, reinforcement and template quantities of the final wall, beam, plate, column and stair by using a calculation formula, and generating engineering quantity and valuation list by combining local engineering quota data, namely realizing automatic prediction of building engineering structure calculation quantity based on CAD drawing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211485132.9A CN116403234A (en) | 2022-11-24 | 2022-11-24 | Automatic prediction method for building engineering structure calculation based on CAD drawing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211485132.9A CN116403234A (en) | 2022-11-24 | 2022-11-24 | Automatic prediction method for building engineering structure calculation based on CAD drawing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116403234A true CN116403234A (en) | 2023-07-07 |
Family
ID=87018519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211485132.9A Pending CN116403234A (en) | 2022-11-24 | 2022-11-24 | Automatic prediction method for building engineering structure calculation based on CAD drawing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116403234A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391332A (en) * | 2023-09-07 | 2024-01-12 | 中铁一局集团有限公司 | Engineering quantity calculation list hanging method, device, computer equipment and storage medium |
-
2022
- 2022-11-24 CN CN202211485132.9A patent/CN116403234A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391332A (en) * | 2023-09-07 | 2024-01-12 | 中铁一局集团有限公司 | Engineering quantity calculation list hanging method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112561487B (en) | Method, device and equipment for calculating construction progress and readable storage medium | |
| CN110689607B (en) | System, method, computer readable storage medium and apparatus for drawing recognition and three-dimensional modeling | |
| CN108460189A (en) | A kind of curtain wall mounting design method based on BIM technology | |
| CN114511202A (en) | BIM-based full-period engineering project management method and platform | |
| Garwood et al. | A framework for producing gbXML building geometry from Point Clouds for accurate and efficient Building Energy Modelling | |
| CN116403234A (en) | Automatic prediction method for building engineering structure calculation based on CAD drawing | |
| CN108846152A (en) | Assembly of shear wall structure based on BIM lifts stage place optimization placement method | |
| CN116993928B (en) | Urban engineering mapping method and system based on unmanned aerial vehicle remote sensing technology | |
| CN112347533B (en) | Building structure BIM forward automatic checking method based on Revit | |
| CN112560134A (en) | Batch deepening design method of assembled structure laminated slab based on CAD and BIM | |
| CN111395520A (en) | Prefabricated column and superposed beam deep design method based on CAD and WebGl fabricated structures | |
| CN105718616A (en) | Reinforcement detailing production computation management method based on BIM (Building Information Modeling) | |
| CN113392256A (en) | Edge component object generation method, device, equipment and storage medium | |
| KR101735072B1 (en) | Environmental load estimating device and method for civil infrastructure in the planning stage | |
| CN116777678A (en) | Power transmission line tower construction progress monitoring method based on multi-source data | |
| Hassan et al. | Real-time road cracks detection based on improved deep convolutional neural network | |
| CN115422634A (en) | Concrete beam BIM modeling system | |
| CN107784409A (en) | Project templet project management system based on BIM | |
| CN115081695A (en) | BIM model-based engineering budget method, system and terminal equipment | |
| Cho et al. | Cost estimating methods for RC structures by quantity takeoff and quantity prediction in the design development stage | |
| CN113821860B (en) | Method, device, equipment and storage medium for determining break point on steel bar graphic element | |
| CN114266090A (en) | Assembly type building construction monitoring method based on unmanned aerial vehicle technology | |
| Chowdhury et al. | Generating integrated bill of materials using mask R-CNN artificial intelligence model | |
| Puri et al. | Toward automated dimensional quality control of precast concrete elements using design BIM | |
| CN112699452A (en) | Construction method for improving flatness of large-area terrace |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |